GPT-Image2-Skill
GPT Image 2/2.5 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing
What is GPT-Image2-Skill?
GPT Image 2/2.5 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing
Overview of GPT-Image2-Skill
What it is
GPT-Image2-Skill is a prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation and editing. It supports GPT Image 2, 2.5, and 2.6 models. The gallery contains 171 numbered entries across 31 categories. The project provides two agent skills and a CLI that can be used with skill-capable agent runtimes such as Claude Code, Codex, OpenClaw, and Hermes Agent. Documentation is available in English and Chinese.
Key features
- Gallery of 171 prompts across 31 categories with selected reference images
- Two agent skills:
gpt-imagefor generating and editing images, andget-prompt-from-imagefor extracting prompts from existing images - CLI that defaults to GPT Image 2.6 Flare model
- Supports image-reference formats including PNG, WebP, and JPG
- Capable of generating animations from sprite sheets and creating websites from images
- Includes creative workflows for animation and web generation
Use cases
- Generating and editing images using GPT Image models with custom prompts and reference images
- Extracting prompts from existing images for reuse or modification
- Creating animated GIFs from sprite sheets (e.g., eight-cell sheet to GIF)
- Converting images into interactive webpages with clickable elements
- Producing vector-style diagrams, icons, and slide layouts for presentations
Getting started
See the repository README for installation and quick start instructions.
License and pricing
This project is licensed under the MIT License and is open source.
Based on the project's public README and repository metadata.